Seismic Velocity Structure Beneath the Tofino Forearc Basin Using Full Waveform Inversion

Given the effects of steep dips and large lateral variations in seismic velocity beneath the Vancouver Island continental shelf, seismic processing and travel time inversion are inadequate to obtain a detailed velocity model of the subsurface. Therefore, seismic full waveform inversion is applied to multichannel seismic reflection data to obtain a high-resolution velocity model beneath the Tofino fore-arc basin under the continental shelf off Vancouver Island margin. Seismic velocities obtained in this study help in understanding the shallow shelf sediment structures, as well as the deeper structures associated with accreted terranes, such as Pacific Rim and Crescent terranes. Shallow high velocities, as large as ∼5 km/s, were modeled in the mid-shelf region at ∼1.5–2.0 km depth. These coincide with an anticlinal structure in the seismic data, and possibly indicate the shallowest occurrence of the volcanic Crescent terrane. In general, seismic velocities increase landward, indicating sediment over-consolidation related to the compressional regime associated with the ongoing subduction of the Juan de Fuca plate and the emplacement of Pacific Rim and Crescent accreted terranes. Seismic velocities show a sharp increase about 10 km west of Vancouver Island, possibly indicating an underlying transition to the Pacific Rim terrane. A prominent low velocity zone extending over 10 km is observed in the velocity model at 800–900 m below the seafloor. This possibly indicates the presence of a high porosity layer associated with lithology changes. Alternatively, this may indicate fluid over-pressure or over-pressured gas in this potential hydrocarbon environment.

Research on the Estimate of Gas Hydrate Saturation Based on LSTM Recurrent Neural Network

Gas hydrate saturation is an important index for evaluating gas hydrate reservoirs, and well logs are an effective method for estimating gas hydrate saturation. To use well logs better to estimate gas hydrate saturation, and to establish the deep internal connections and laws of the data, we propose a method of using deep learning technology to estimate gas hydrate saturation from well logs. Considering that well logs have sequential characteristics, we used the long short-term memory (LSTM) recurrent neural network to predict the gas hydrate saturation from the well logs of two sites in the Shenhu area, South China Sea. By constructing an LSTM recurrent layer and two fully connected layers at one site, we used resistivity and acoustic velocity logs that were sensitive to gas hydrate as input. We used the gas hydrate saturation calculated by the chloride concentration of the pore water as output to train the LSTM network. We achieved a good training result. Applying the trained LSTM recurrent neural network to another site in the same area achieved good prediction of gas hydrate saturation, showing the unique advantages of deep learning technology in gas hydrate saturation estimation.

Microstructural characteristics of natural gas hydrates hosted in various sand sediments

Natural gas hydrates form as floating model in pores, without being affected by grain sizes and sand wettability.